Proceedings Article10.1109/ICME.2002.1035566
Spatial auditory processing for a hearing robot
Jie Huang
- 07 Nov 2002
- Vol. 2, pp 253-256
8
TL;DR: An auditory system for a multimodal mobile robot that contains four microphones that are spatially arranged on a spherical robot head with three around the side of the sphere and one at the top containing a model of the precedence effect is described.
read more
Abstract: We describe an auditory system for a multimodal mobile robot. The auditory system contains four microphones that are spatially arranged on a spherical robot head with three around the side of the sphere and one at the top. Different pairs of microphones provide localization cues for different directions. By using the top-mounted microphone, the elevation of sound sources can also be localized based on time difference and intensity difference cues. Different methods of spatial cue integration are proposed and compared. By incorporating a model of the precedence effect, the influence of echoes and reverberations can be inhibited.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Environmental Sound Recognition With Time–Frequency Audio Features
TL;DR: An empirical feature analysis for audio environment characterization is performed and a matching pursuit algorithm is proposed to use to obtain effective time-frequency features to yield higher recognition accuracy for environmental sounds.
CNN hyper-parameter optimization for environmental sound classification
TL;DR: In this article , the Particle Swarm Optimization (PSO) algorithm was rearranged to represent the CNN architecture and the hyper-parameters in CNN were represented exactly without any transformation during optimization.
41
A semi-supervised learning approach to online audio background detection
Selina Chu,Shrikanth S. Narayanan,C.-C. Jay Kuo +2 more
- 19 Apr 2009
TL;DR: This work proposes a method for learning the initial background model using a semi-supervised learning approach, which is integrated into the online background determination process, providing a more complete background model.
15
•Proceedings Article
Unstructured audio classification for environment recognition
Selina Chu
- 13 Jul 2008
TL;DR: This research will investigate challenging issues in characterizing environmental sounds such as the development of appropriate features extraction algorithm and learning techniques for modeling the dynamics of the environment.
Çevresel sesleri̇n evri̇şi̇msel si̇ni̇r ağlari i̇le siniflandirilmasi
01 Jun 2023
TL;DR: In this article , anlamda Çevresel Seslerin Sınıflandırılması (ÇSS) kritik önem kazanmaktadır.
References
Multiple emitter location and signal parameter estimation
TL;DR: In this article, a description of the multiple signal classification (MUSIC) algorithm, which provides asymptotically unbiased estimates of 1) number of incident wavefronts present; 2) directions of arrival (DOA) (or emitter locations); 3) strengths and cross correlations among the incident waveforms; 4) noise/interference strength.
14K
Multiple emitter location and signal Parameter estimation
R. O. Schmidt
- 01 Jan 1979
TL;DR: The multiple signal classification (MUSIC) algorithm is described, which provides asymptotically unbiased estimates of number of incident wavefronts present and directions of arrival (DOA) (or emitter locations) and strengths and cross correlations among the incident waveforms.
8.4K
•Book
Spatial Hearing: The Psychophysics of Human Sound Localization
Jens Blauert
- 31 Dec 1983
TL;DR: In this article, the physics of the external ear (transfer functions of external ear, area function and termination of the ear canal, analysis of transfer characteristics) evaluation of monaural attributes of ear input signals (lateralization and multiple auditory events, summing localization and the law of the first wavefront, inhibition of the primary sound) two sound sources radiating partially coherent or incoherent signals (the influence of the degree of coherence, binaural signal detection) more than two sound source and diffuse sound fields.
2.5K
Maximum likelihood methods for direction-of-arrival estimation
Petre Stoica,Ken Sharman +1 more
TL;DR: Five methods of direction-of-arrival (DOA) estimation which can be derived from the maximum-likelihood (ML) principle are considered and one of them, MODE-2, is obtained by using the ML principle on the statistics of certain linear combinations of the sample eigenvectors.
941